[openib-general] opensm and faulty hardware

Hal Rosenstock halr at voltaire.com
Tue Sep 27 11:21:06 PDT 2005


Hi Viswa,

On Tue, 2005-09-27 at 14:13, Viswanath Krishnamurthy wrote:
> I tracked down the issue to a bug in osm_lid_mgr.c 
> 
> function:  __osm_lid_mgr_init_sweep(...)
> 
> The bad hardware was retutning an assigned LID of 0xFFFF. In this
> function there is a loop
> as follows where opensm is getting stuck.. (with line number)
> 
>     392   p_port_guid_tbl = &p_mgr->p_subn->port_guid_tbl;
>     393
>     394   for( p_port = (osm_port_t*)cl_qmap_head( p_port_guid_tbl );
>     395        p_port != (osm_port_t*)cl_qmap_end( p_port_guid_tbl );
>     396        p_port = (osm_port_t*)cl_qmap_next( &p_port->map_item )
> )
>     397   {
>     398     osm_port_get_lid_range_ho(p_port, &disc_min_lid,
> &disc_max_lid);
>     399     for (lid = disc_min_lid; lid <= disc_max_lid;
> lid++)                  <===== Bug here
>     400       cl_ptr_vector_set(p_discovered_vec, lid, p_port );
>     401   }
> 
> Since the disc_max_lid and disc_min_lid are 0xFFFF, and these are
> unsigned 16 bit numbers, the condition

0xFFFF is the permissive LID and not LID routed. In fact, unicast LIDs
should be between 0x0001 and 0xbfff.

So I think the fix involves not allowing min/max to be set that way.

> in the for loop never becomes false, and opensm is stuck in the loop. 
> There are couple of other places in that
> function that needs fixing too.

What are the other places you see ?

Thanks.

-- Hal




More information about the general mailing list